thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 6

CUDA: fix padding of GQA to power of 2 in FA (#19115)

Browse source
This commit is contained in:
Johannes Gäßler 2026-01-26 23:24:58 +01:00 • committed by GitHub
parent 8f80d1b254
commit b0311c16d2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 64 additions and 52 deletions
Download patch file Download diff file Expand all files Collapse all files

4
tests/test-backend-ops.cpp
View file

@ -8216,8 +8216,8 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
for (int nh : { 4, }) {
for (int nr3 : { 1, 3, }) {
if (hsk > 64 && nr3 > 1) continue; // skip broadcast for large head sizes
for (int nr2 : { 1, 4, 16 }) {
if (nr2 == 16 && hsk != 128) continue;
for (int nr2 : { 1, 4, 12 }) {
if (nr2 == 12 && hsk != 128) continue;
//for (int kv : { 1, 17, 31, 33, 61, 113, 65, 127, 129, 130, 255, 260, 371, 380, 407, 512, 1024, }) {
for (int kv : { 113, 512, 1024, }) {
if (nr2 != 1 && kv != 512) continue;